E0 270: Machine Learning, February Term 2021
E0 270: Machine Learning
Department of Computer Science & Automation
Indian Institute of Science
Lectures: Tuesday, Thursday 11:30am-01:00pm
First lecture: Thu, Feb 25th
Tutorial/discussion sessions will be scheduled on an on-going basis.
Prof. Ambedkar Dukkipati
Course Evaluation (Final)
Mid Term: 20 Marks
Assignments: 30 Marks
Participation in the Discussion and Doubt Solving: 10 Marks
Project mid evaluation: 10 Marks
Project Final evaluation: 30 Marks
- Check Teams time to time.
With the increasing amounts of data being generated in diverse fields
such as astronomical sciences, health and life sciences, financial and
economic modeling, climate modeling, market analysis, and even defense,
there is an increasing need for computational methods that can
automatically analyze and learn predictive models from such data.
Machine learning, the study of computer systems and algorithms that
automatically improve performance by learning from data, provides such
methods; indeed, machine learning techniques are already being used with
success in a variety of domains, for example in computer vision to
develop face recognition systems, in information retrieval to improve
search results, in computational biology to discover new genes, and in
drug discovery to prioritize chemical structures for screening. This
course aims to provide a sound introduction to both the theory and
practice of machine learning, with the goal of giving students a strong
foundation in the subject, enabling them to apply machine learning
techniques to real problems, and preparing them for advanced
coursework/research in machine learning and related fields.
E0 232: Probability and Statistics (or equivalent course elsewhere) and earned a grade of B or higher.
In addition, some background in linear algebra and optimization will be helpful.
As students of IISc, we expect you to adhere to the highest standards of academic honesty and integrity.
Elements of the course are designed to support your learning of the
subject. Copying will not help you (in the exams or in the real world),
so don't do it. If you have difficulties learning some of the topics or
lack some background, try to form study groups where you can bounce off
ideas with one another and try to teach each other what you understand.
You're also welcome to talk to any of us and we'll be glad to help you.
If any exam/report is found to be copied, it will automatically
result in a zero grade for that exam/project and a warning note to
your advisor. Any repeat instance will automatically lead to a failing
grade in the course.
Course Material (Topic wise)
||Introduction, What is Data and Model, Machine Learning Workflow, Distance Based Classifiers, Bayes Decision Theory
||Different types of Learning, Supervised Learning, Foundational Aspects of ML, Linear Regression
||Probabilistic view of Linear Regression, Logistic Regression, Hyperplane based Classifiers and Perceptron
||Support Vector Machines, Kernel Methods
||Feed Forward Neural Networks, Backpropagation algorithm, CNNs, RNNs
||Unsupervised Learning, Dimentionality Reduction, K-Means Clustering
||Probabilistic Models, Graphical Models, Markov Random Fields, Markov Chain, Monte Carlo Methods, Restricted Boltzmann Machines
||see lecutre video
||Latent Variable Models, Gaussian Mixture Models, Free Energy Optimization, Expectation Maximization algorithm
||see lecutre video
||Model Selection, Making ML algorithms work
||Linear Regression, Logistic Regression, Naive Bayes, Bayes Decision Theory
||March 23, 2021
||Shubham Gupta, Nabanita Paul
||Generative modeling - GANs and VAEs
||Autoencoder and RNNs
||May 1, 2021
- C.M. Bishop, Pattern Recognition and Machine Learning. Springer, 2006.
- Hastie T, Tibshirani R and Friedman J, The Elements of Statistical Learning: Data Mining, Inference and Prediction, Springer, 2nd Edition, 2009
- Haykin. S, Neural Networks and Learning Systems, Prentice-Hall, 3rd Edition, 2009
- Goodfellow, Bengio, Courville, Deep Learning, MIT Press, 2017
- T. Hastie, R. Tibshirani and J. Friedman, The Elements of
Statistical Learning: Data Mining, Inference and Prediction. Springer,
2nd Edition, 2009.
[free download available]
- T. Mitchell, Machine Learning. McGraw Hill, 1997.
As part of the this course, you are required to work on a project. This will give you hands-on experience of working with data from various domains - text,
images, videos etc that are used in the contemporary ML research, and also expose you to some specialized topics of ML that are more advanced or recent than what will be
covered in the lectures.
A list of project ideas will be mailed on the mailing list. You can also come up with your own projects ideas.
- Some projects ideas are based on reading and survey of several papers, and others are based on implementation of one or two papers, and comparison of the methods proposed in them over datasets. We will point you to relevant papers and datasets. You can read/implement other relevant papers and datasets if you want. You can also innovate and come up with your own approaches for solving the problems.
- The best grades will be reserved for the groups which come up with some new approaches, either theoretically or experimentally, which have not been used in the literature.
- Each project will have an associated project mentor. He/she will help you to locate papers and datasets, and clear doubts.
- In implementation-based projects, it may so happen that codes are already available online. It is perfectly fine to use them. Only, that should be cited in the reports.
- You are required to provide a mid-term report around the third week of March, and the final report shortly before the final examination.
- Plagiarism is strictly prohibited while writing the reports. Any plagiarism detected will result in F grade for the course.
Course Project PresentationWill be updated later